ggml-cpu : disable GGML_NNPA by default due to instability (llama/14880)

* docs: update s390x document for sentencepiece

Signed-off-by: Aaron Teo <redacted>
(cherry picked from commit e086c5e3a7ab3463d8e0906efcfa39352db0a48d)

* docs: update huggingface links + reword

Signed-off-by: Aaron Teo <redacted>
(cherry picked from commit 8410b085ea8c46e22be38266147a1e94757ef108)

* ggml-cpu: disable ggml-nnpa compile flag by default

fixes #14877

Signed-off-by: Aaron Teo <redacted>
(cherry picked from commit 412f4c7c88894b8f55846b4719c76892a23cfe09)

* docs: update s390x build docs to reflect nnpa disable

Signed-off-by: Aaron Teo <redacted>
(cherry picked from commit c1eeae1d0c2edc74ab9fbeff2707b0d357cf0b4d)

---------

Signed-off-by: Aaron Teo <redacted>

diff --git a/CMakeLists.txt b/CMakeLists.txt
index 8ca1053cab3205c02b9f0038fa4f941135eef251..20467c54da1020bedc8c5d6e685fd056eac757fe 100644 (file)
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -131,7 +131,7 @@ option(GGML_RVV              "ggml: enable rvv"              ON)
 option(GGML_RV_ZFH           "ggml: enable riscv zfh"        OFF)
 option(GGML_XTHEADVECTOR     "ggml: enable xtheadvector"     OFF)
 option(GGML_VXE              "ggml: enable vxe"              ON)
-option(GGML_NNPA             "ggml: enable nnpa"             ON)
+option(GGML_NNPA             "ggml: enable nnpa"             OFF)  # temp disabled by default, see: https://github.com/ggml-org/llama.cpp/issues/14877
 
 option(GGML_CPU_ALL_VARIANTS "ggml: build all variants of the CPU backend (requires GGML_BACKEND_DL)" OFF)
 set(GGML_CPU_ARM_ARCH        "" CACHE STRING "ggml: CPU architecture for ARM")

diff --git a/src/ggml-cpu/CMakeLists.txt b/src/ggml-cpu/CMakeLists.txt
index 2cc42d4b02af95511144e5e220317a3e529fd844..f188d1638dc5ddb8d804c0f54a14bbee09a96859 100644 (file)
--- a/src/ggml-cpu/CMakeLists.txt
+++ b/src/ggml-cpu/CMakeLists.txt
@@ -458,6 +458,7 @@ function(ggml_add_cpu_backend_variant_impl tag_name)
             list(APPEND ARCH_FLAGS -march=z16)
         elseif (${S390X_M} MATCHES "9175|9176")
             # NOTE: Only available from GCC 15.1.0 onwards. Any z17 machine with compile issues must first verify their GCC version.
+            #       binutils must also be updated to the latest for the -march=z17 flag to work. Otherwise, use -march=arch15.
             message(STATUS "z17 target")
             list(APPEND ARCH_FLAGS -march=z17)
         else()